openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Apr 24, 2026 · AMD Ryzen 5 5500
codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
Global Score
90 vs 67
Hardware Fit
88 vs 67
Quality Score
91 vs 67
Hardware
openai/gpt-oss-20b codestral:22b
MachineASUSNVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 5 5500Cortex-X925
Cores1220
RAM31 GB122 GB
GPUNavi 44 [Radeon RX 9060 XT]Device 2e12
OSNobara Linux 43Ubuntu 24.04.4 LTS
Archx64arm64
Power Modeperformanceperformance
Performance
openai/gpt-oss-20b codestral:22b
Tokens/sec58.717.2
First chunk6 ms129 ms
TTFT4.5 s129 ms
Load timeN/A11.6 s
Memory usage11.9 GB18.9 GB
Memory %38%16%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
28/30
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
Quality
openai/gpt-oss-20b
Reasoning
18/20
Coding
15/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
codestral:22b
Reasoning
11/20
Coding
17/20
Instruction
9/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest